{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T10:07:35Z","timestamp":1772446055697,"version":"3.50.1"},"reference-count":30,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T00:00:00Z","timestamp":1772236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Intelligent Surveillance Sphere Technology","award":["H20251385"],"award-info":[{"award-number":["H20251385"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Reliable fault detection along transmission corridors is essential for preventing small defects from developing into long outages and costly emergency operations. This study aims to improve the field reliability of an open vocabulary vision language backbone without retraining the large model in an end-to-end manner. The work focuses on four operational fault classes in multi-region corridor imagery collected during routine inspections and uses a Florence-2 vision language model as the base recognizer. On top of this backbone, three domain-specific components are introduced. A subclass-aware fusion scheme keeps probability mass within the active parent concept so that insulator icing and conductor icing produce stable, action-oriented decisions. A Power-Line Focus Then Crop normalization uses an attention-guided corridor window together with isotropic resizing so that thin conductors and small fittings remain visible in the processed image. A corridor geo prior reduces scores as the distance from the mapped centerline increases and in this way suppresses detections that lie outside the corridor. All methods are evaluated under a shared preprocessing and scoring pipeline in training-free and parameter-efficient tuning modes. Experiments on unseen regions show higher accuracy for skinny and low-contrast faults, fewer false alarms outside the right-of-way, and improved score calibration in the confidence range used for triage, while keeping throughput and memory usage suitable for unmanned aerial vehicles and substation edge devices.<\/jats:p>","DOI":"10.3390\/jimaging12030106","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T08:51:57Z","timestamp":1772441517000},"page":"106","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Vision\u2013Language Models for Transmission Line Fault Detection: A New Approach for Grid Reliability and Optimization"],"prefix":"10.3390","volume":"12","author":[{"given":"Runle","family":"Yu","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Chongqing University, Chongqing 400044, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihao","family":"Mai","sequence":"additional","affiliation":[{"name":"School of Electrical, Computer and Energy Engineering, Arizona State University, 551 East Tyler Mall, Tempe, AZ 85281, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5267-1303","authenticated-orcid":false,"given":"Yang","family":"Weng","sequence":"additional","affiliation":[{"name":"School of Electrical, Computer and Energy Engineering, Arizona State University, 551 East Tyler Mall, Tempe, AZ 85281, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3471-3936","authenticated-orcid":false,"given":"Qiushi","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Chongqing University, Chongqing 400044, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guochang","family":"Xu","sequence":"additional","affiliation":[{"name":"State Grid Henan Electric Power Company, Zhengzhou 450052, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengliang","family":"Ren","sequence":"additional","affiliation":[{"name":"Henan Jiuyu EPRI Electric Power Technology Co., Ltd., Zhengzhou 450052, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"824","DOI":"10.3390\/rs9080824","article-title":"Automatic Power Line Inspection Using UAV Images","volume":"9","author":"Zhang","year":"2017","journal-title":"Remote Sens."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Santos, T., Cunha, T., Dias, A., Moreira, A.P., and Almeida, J. (2024). UAV Visual and Thermographic Power Line Detection Using Deep Learning. Sensors, 24.","DOI":"10.3390\/s24175678"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Byrne, J., Dorrian, M., McCarthy, T., and Laefer, D.F. (2017). 3D Reconstructions Using Unstabilized Video Footage from an Unmanned Aerial Vehicle. J. Imaging, 3.","DOI":"10.3390\/jimaging3020015"},{"key":"ref_4","first-page":"111595","article-title":"UAV\u2013LiDAR Aids Automatic Intelligent Powerline Inspection","volume":"229","author":"Guan","year":"2021","journal-title":"Eng. Struct."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"107455","DOI":"10.1016\/j.engappai.2023.107455","article-title":"Small Object Detection in Unmanned Aerial Vehicle Images Using Multi-Scale Hybrid Attention","volume":"128","author":"Song","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"9280","DOI":"10.1109\/TII.2022.3227638","article-title":"Component Detection for Power Line Inspection Using a Graph-Based Relation Guiding Network","volume":"19","author":"Liu","year":"2023","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"98","DOI":"10.3390\/jimaging4080099","article-title":"Long-Term Monitoring of Crack Patterns with UAV Imagery: Calibration and SLAM with Planar Markers","volume":"4","author":"Germanese","year":"2018","journal-title":"J. Imaging"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Santagata, T. (2017). Monitoring of the Nirano Mud Volcanoes Regional Natural Reserve (North Italy) Using Unmanned Aerial Vehicles and Terrestrial Laser Scanning. J. Imaging, 3.","DOI":"10.3390\/jimaging3040042"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"4121","DOI":"10.3390\/rs16132465","article-title":"A Small-Object Detection Model Based on Improved YOLOv8s","volume":"16","author":"Ni","year":"2024","journal-title":"Remote Sens."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Kan, B., Wang, T., Lu, W., Zhen, X., Guan, W., and Zheng, F. (2023). Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models. arXiv.","DOI":"10.1109\/ICCV51070.2023.01436"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"3468","DOI":"10.1109\/TSG.2022.3168904","article-title":"Fault Location in Power Networks Using a Sparse Set of Digital Fault Recorders","volume":"13","author":"Galvez","year":"2022","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_12","unstructured":"Zhang, R., Fang, R., Zhang, W., Gao, P., Li, K., Dai, J., Qiao, Y., and Li, H. (2021). Tip-Adapter: Training-Free CLIP-Adapter for Better Vision\u2013Language Modeling. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Xiao, B., Wang, H., Xu, W., Dai, X., Lu, H., Lu, Y., Zeng, M., Liu, C., and Yuan, L. (2023). Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks. arXiv.","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref_14","unstructured":"Zhou, K., Yang, J., Loy, C.C., and Liu, Z. (2021). Learning to Prompt for Vision-Language Models. arXiv."},{"key":"ref_15","unstructured":"Gao, P., Geng, S., Zhang, R., Ma, T., Fang, R., Zhang, Y., Li, H., and Qiao, Y. (2021). CLIP-Adapter: Better Vision-Language Models with Feature Adapters. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2516","DOI":"10.1109\/TPWRS.2021.3125613","article-title":"Solar Panel Identification via Deep Semi-Supervised Learning and Deep One-Class Classification","volume":"37","author":"Cook","year":"2022","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3530710","DOI":"10.1109\/TIM.2024.3453332","article-title":"CACS-YOLO: A Lightweight Model for Insulator Defect Detection Based on Improved YOLOv8m","volume":"73","author":"Cao","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_18","unstructured":"Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wang, Q., Liu, G., and Wang, B. (2024). CapS-Adapter: Caption-Based MultiModal Adapter in Zero-Shot Classification. arXiv.","DOI":"10.1145\/3664647.3681566"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2516","DOI":"10.1109\/TSG.2016.2546181","article-title":"Data-Driven Power Outage Detection by Social Sensors","volume":"7","author":"Sun","year":"2016","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2058","DOI":"10.1109\/TPWRD.2006.876659","article-title":"Fault Detection and Classification in Transmission Lines Based on Wavelet Transform and ANN","volume":"21","author":"Silva","year":"2006","journal-title":"IEEE Trans. Power Deliv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1109\/TPWRD.2007.893596","article-title":"Transmission Line Boundary Protection Using Wavelet Transform and Neural Network","volume":"22","author":"Zhang","year":"2007","journal-title":"IEEE Trans. Power Deliv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1109\/JPETS.2018.2881429","article-title":"Intelligent Monitoring and Inspection of Power Line Components Powered by UAVs and Deep Learning","volume":"6","author":"Nguyen","year":"2019","journal-title":"IEEE Power Energy Technol. Syst. J."},{"key":"ref_24","unstructured":"Das, L., Saadat, M.H., Gjorgiev, B., Auger, E., and Sansavini, G. (2022). Object Detection-Based Inspection of Power Line Insulators: Incipient Fault Detection in the Low Data-Regime. arXiv."},{"key":"ref_25","first-page":"291","article-title":"Evaluation of Power System Reliability Incorporating Protection System Miscoordination","volume":"26","author":"Sbaihema","year":"2024","journal-title":"Azerbaijan J. Electr. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"3289","DOI":"10.1109\/TMECH.2023.3340312","article-title":"Hierarchical Viewpoint Planning for Complex Surfaces in Industrial Product Inspection","volume":"29","author":"Wang","year":"2024","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhang, L., Wang, Y., Zhou, J., Zhang, C., Zhang, Y., Guan, J., Bian, Y., and Zhou, S. (2022, January 10\u201314). Hierarchical Few-Shot Object Detection: Problem, Benchmark and Method. Proceedings of the 30th ACM International Conference on Multimedia, Lisbon, Portugal.","DOI":"10.1145\/3503161.3548412"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1007\/s10462-025-11186-x","article-title":"Context in Object Detection: A Systematic Literature Review","volume":"58","author":"Jamali","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Hoefler, M.A., Mueller, K., and Samek, W. (2024). XAI-Guided Insulator Anomaly Detection for Imbalanced Datasets. arXiv.","DOI":"10.1007\/978-3-031-92805-5_5"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Huang, R., Liu, Z., Chen, J., Shi, Y., and Xiao, G. (2023, January 8\u201311). Geometric Prior-Assisted Feature Presentation Enhancement for Object Detection in Aerial Images. Proceedings of the 2023 IEEE International Conference on Image Processing (ICIP), Kuala Lumpur, Malaysia.","DOI":"10.1109\/ICIP49359.2023.10222806"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/3\/106\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T09:27:32Z","timestamp":1772443652000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/3\/106"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,28]]},"references-count":30,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["jimaging12030106"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12030106","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,28]]}}}